Real time face detection using haar-like feature method and local binary pattern method

Tarumanagara International Conference on the Applications of Technology and Engineering

工业技术（总论）

Junaidy, D.^1 ; Wulandari, M.^1 ; Tanudjaja, H.^2

Electrical Engineering Department, Faculty of Engineering, Universitas Tarumanagara, Jakarta, Indonesia^1

Electrical Engineering Department, Faculty of Engineering Universitas Katolik Indonesia Atma Jaya, Jakarta, Indonesia^2

关键词: Engineering department;    Face identification;    Haar-like features;    Local binary patterns;    Real-time face detection;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/508/1/012076/pdf
DOI  :  10.1088/1757-899X/508/1/012076

学科分类：工业工程学

来源: IOP

【 摘 要 】

Face detection is one of the important roles in face identification. There are some difficulty factors in the process. Therefore, some methods are developed. This study aims to compare Haar-Like Feature method and Local Binary Pattern (LBP) method for face detection. Samples are 25 people in the Electric Engineering Department. Based on the result, Haar-Like Feature method is more accurate than LBP method. Haar-Like method can detect 20 faces from 25 faces with success rate of 80% while LBP can detect 14 faces from 25 faces with success rate of 56%. From this research, it is taken that both methods are having in trouble detecting face from someone that use glasses, have dark skin, or having facial hair.